Vehicle-road intelligent cooperative road government work order generation method and system

Abstract

The invention relates to the technical field of data processing, and provides a vehicle-road intelligent cooperative road government work order generation method and system. The method comprises the following steps: cooperatively acquiring vehicle-road state data of a target road through a vehicle-mounted terminal and a road side unit; verifying road damage based on the vehicle and road state data, and generating a disease verification result; carrying out maintenance authentication according to a verification result, collecting traffic flow and dynamically calculating a maintenance priority; returning the target road, the verification result and the priority to the system, filling the work order template according to fields, and generating a first road government work order; and connecting a service distribution system, and executing distribution and evidence storage management of the work order. The technical problems of low work order generation efficiency and poor accuracy caused by manual input and insufficient data verification of traditional road government work order generation are solved, and the technical effects of collecting vehicle-road state data through the vehicle terminal and the road side unit, automatically verifying road diseases and improving the automation degree and accuracy of road government work order generation are achieved.

Description

Technical Field

[0001] This application relates to the technical field of data processing, and particularly to a method and system for generating road work orders with intelligent vehicle-road collaboration. Background Art

[0002] With the continuous development of the transportation industry, the maintenance and management of roads have become key tasks to ensure traffic safety and smoothness. Traditional methods for generating road work orders usually rely on manual input and on-site inspections, which are not only time-consuming and laborious, but also due to human factors and incomplete data collection, the accuracy and efficiency of work orders are often not guaranteed. Traditional methods lack systematic collaboration means in aspects such as road disease detection, damage assessment, and calculation of repair priorities, making it difficult to efficiently process a large amount of road information, resulting in waste of resources and delays in repair work. Summary of the Invention

[0003] This application provides a method and system for generating road work orders with intelligent vehicle-road collaboration, aiming to solve the technical problems that traditional road work order generation relies on manual input and data verification is insufficient, resulting in low work order generation efficiency and poor accuracy.

[0004] In the first aspect disclosed by this application, a method for generating a road work order with intelligent vehicle-road collaboration is provided. The method includes: collaboratively collecting vehicle-road state data of a target road through an on-vehicle terminal and a roadside unit, where the vehicle-road state data includes vehicle vibration characteristics, road surface images, and laser point cloud data; collaboratively verifying road damage based on the vehicle-road state data to generate a road disease verification result; performing road repair certification according to the road disease verification result, collecting traffic flow of the roads that pass the certification, and dynamically calculating the repair priority by combining the road disease verification result and the traffic flow collection result; returning the target road, the road disease verification result, and the repair priority to the system, filling the content into a work order template according to field names to generate a first road work order, where the first road work order has a first adaptation label; connecting to a service distribution system and performing distribution and deposit management of the first road work order based on the service distribution system.

[0005] Another aspect disclosed in the present application provides a road work order generation system for intelligent vehicle-road collaboration. The system includes: a data collection module: collaboratively collecting vehicle-road state data of a target road through an in-vehicle terminal and a roadside unit, where the vehicle-road state data includes vehicle vibration characteristics, road surface images, and laser point cloud data; a collaborative verification module: collaboratively verifying road damage based on the vehicle-road state data to generate a road disease verification result; a priority calculation module: performing road maintenance certification according to the road disease verification result, collecting traffic flow of the roads passing the certification, and dynamically calculating the maintenance priority in combination with the road disease verification result and the traffic flow collection result; a work order generation module: returning the target road, the road disease verification result, and the maintenance priority to the system, filling the content into a work order template according to field names to generate a first road work order, where the first road work order has a first adaptation label; a work order distribution module: connecting to a service distribution system and performing distribution and deposit management of the first road work order based on the service distribution system.

[0006] One or more technical solutions provided in the present application have at least the following technical effects or advantages:

[0007] The above-mentioned method for generating a road work order for intelligent vehicle-road collaboration first collaboratively collects vehicle-road state data of a target road through an in-vehicle terminal and a roadside unit, where the vehicle-road state data includes vehicle vibration characteristics, road surface images, and laser point cloud data. Subsequently, it collaboratively verifies road damage based on the vehicle-road state data to generate a road disease verification result. Then, it performs road maintenance certification according to the road disease verification result, collects traffic flow of the roads passing the certification, and dynamically calculates the maintenance priority in combination with the road disease verification result and the traffic flow collection result. Then, it returns the target road, the road disease verification result, and the maintenance priority to the system, fills the content into a work order template according to field names to generate a first road work order, where the first road work order has a first adaptation label. Finally, it connects to a service distribution system and performs distribution and deposit management of the first road work order based on the service distribution system. It achieves the technical effect of improving the automation degree and accuracy of road work order generation.

[0008] The above description is only an overview of the technical solutions of the present application. In order to be able to understand the technical means of the present application more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features, and advantages of the present application more obvious and understandable, the following specifically illustrates the embodiments of the present application. Description of the Drawings

[0009] To more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the accompanying drawings required for description in the embodiments. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can be obtained based on these drawings.

[0010] Figure 1 It is a schematic flowchart of a method for generating a road work order for vehicle-road intelligent collaboration in an embodiment.

[0011] Figure 2 It is an architecture diagram of a system for generating a road work order for vehicle-road intelligent collaboration in an embodiment.

[0012] Explanation of reference numerals: data acquisition module 11, collaborative verification module 12, priority calculation module 13, work order generation module 14, work order distribution module 15. Detailed implementation manners

[0013] By providing a method and system for generating a road work order for vehicle-road intelligent collaboration in the embodiments of the present application, the technical problems that the traditional generation of road work orders relies on manual input and the data verification is insufficient, resulting in low work order generation efficiency and poor accuracy are solved.

[0014] The following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts belong to the scope of protection of the present application.

[0015] It should be noted that the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or server that includes a series of steps or units does not necessarily have to be limited to those clearly listed steps or units, but may include other steps or modules that are not clearly listed or are inherent to these processes, methods, products, or devices.

[0016] Embodiment 1, as Figure 1 shown, the present application provides a method for generating a road work order for vehicle-road intelligent collaboration, and the method includes:

[0017] Collaboratively collect vehicle-road status data of the target road through an in-vehicle terminal and a roadside unit, where the vehicle-road status data includes vehicle vibration characteristics, road surface images, and laser point cloud data.

[0018] In the embodiment of the present application, in the method for generating a road work order in vehicle-road intelligent collaboration, the on-vehicle terminal and the roadside unit (RSU) work together to collect the vehicle-road state data of the target road. Specifically, the on-vehicle terminal is generally installed on a moving vehicle, and the vibration characteristics of the vehicle are monitored in real time by collecting the vibration data of the vehicle suspension system. These vibration data can reflect the flatness, potholes, etc. of the road surface during vehicle driving. By analyzing these vehicle vibration characteristics, the system can preliminarily judge whether there is damage to the road. At the same time, the roadside unit collects road surface images and lidar point cloud data through cameras and lidar devices deployed along the road. The road surface images can visually capture disease information such as cracks and damages on the road surface, while the lidar point cloud data accurately records the geometric shape and subtle changes of the road surface through three-dimensional scanning technology, providing high-precision spatial information for the accurate identification of road diseases. The collaborative collection of these multi-source data provides a comprehensive and accurate data basis for subsequent road disease detection and work order generation.

[0019] Based on the vehicle-road state data, collaborative verification of road damage is performed to generate a road disease verification result.

[0020] In one embodiment, based on the vehicle-road state data collected by the on-vehicle terminal and the roadside unit, collaborative verification of road damage is performed to generate a road disease verification result. Specifically, the vehicle vibration characteristics obtained by the on-vehicle terminal, the road surface images and lidar point cloud data collected by the roadside unit are input into a road damage verification model for analysis. The vehicle vibration characteristics can be used to preliminarily judge whether there are abnormal vibration areas on the road, so as to locate potential road disease positions; the lidar point cloud data can be used to accurately judge the boundary of the damaged area; the road surface images can be used to detect visible diseases such as cracks and potholes on the road surface. Through the cross-verification of multi-source data, the severity of road diseases can be judged more accurately, and finally a comprehensive road disease verification result is generated. This process not only improves the accuracy of disease identification, but also reduces the subjectivity and error of manual judgment, providing a scientific basis for subsequent maintenance.

[0021] Furthermore, the present application provides the generation of the road disease verification result, including:

[0022] Establish a connection with the on-vehicle terminal through the on-vehicle OBD interface, and obtain the vibration spectrum data of the vehicle suspension system to form vehicle vibration characteristics; use the roadside camera and roadside lidar in the roadside unit to scan and obtain road surface images and lidar point cloud data; activate the road damage verification model, receive the vehicle vibration characteristics, road surface images and lidar point cloud data, perform morphological analysis and verification on the target road, and generate a road disease verification result.

[0023] Preferably, a connection is established with the vehicle terminal through the in-vehicle OBD interface to obtain the vibration spectrum data of the vehicle suspension system in real time. These data reflect the vibration characteristics caused by road surface unevenness or damage during vehicle driving. Then, the vibration spectrum data is identified using the vehicle driving position information to form the vehicle vibration characteristics. Meanwhile, the roadside camera and lidar device in the roadside unit scan the target road respectively. The camera captures road surface images for identifying visible diseases such as cracks and potholes, while the lidar generates high-precision lidar point cloud data through three-dimensional scanning to accurately record the geometric shape and subtle changes of the road surface. Subsequently, the road damage verification model is activated, and the vehicle vibration characteristics, road surface images, and lidar point cloud data are input into the model for comprehensive analysis. The model detects and verifies the road surface through the internal first-level rough screening layer, second-level precise positioning layer, and third-level damage qualitative layer, and finally generates an accurate road disease verification result, including information such as disease type, location, and disease severity score. This process realizes the automatic and precise identification of road damage, significantly improves the efficiency and accuracy of disease detection, and lays a foundation for the generation of subsequent work orders.

[0024] Furthermore, the present application provides that the road damage verification model adopts a cascaded neural network architecture, including:

[0025] The road damage verification model includes a first-level rough screening layer, a second-level precise positioning layer, and a third-level damage qualitative layer; the first-level rough screening layer uses the vehicle vibration characteristics as input data for rough positioning of the disease area and outputs the positioning of the suspicious abnormal section; the second-level precise positioning layer uses the positioning of the suspicious abnormal section and the lidar point cloud data as input data for damage identification and generates an accurate damage area; the third-level damage qualitative layer uses the accurate damage area and the road surface image for damage degree evaluation and generates a road disease verification result.

[0026] Optionally, the road damage verification model adopts a cascaded neural network architecture and is divided into three levels to gradually complete the detection and verification of road diseases, namely the first-level rough screening layer, the second-level precise positioning layer, and the third-level damage characterization layer. Among them, the first-level rough screening layer uses vehicle vibration characteristics as input data. By analyzing the vibration spectrum of the vehicle suspension system, it identifies abnormal vibration areas caused by road unevenness or damage during vehicle driving. These abnormal vibration areas are initially marked as suspicious abnormal road sections, and the positioning information of the suspicious abnormal road sections is output. The main function of this layer is to quickly screen out road sections that may have diseases and narrow the detection range; the second-level precise positioning layer is based on the suspicious abnormal road sections output by the rough screening layer and conducts more refined analysis in combination with laser point cloud data. The laser point cloud data provides high-precision three-dimensional geometric information of the road surface. This layer can accurately identify damage areas such as cracks and potholes on the road surface according to this data, and generate accurate damage area positioning information and feature information (such as damage geometric features, damage texture features, damage type features, etc.), and form precise damage areas for output. The function of this layer is to refine the disease area from rough positioning to pixel-level accuracy and provide accurate spatial information for subsequent damage degree assessment; the third-level damage characterization layer is based on the precise damage areas output by the precise positioning layer and combines road surface image data to evaluate the damage degree. The road surface image provides visual information of the disease. By using image recognition technology to analyze the type of the disease (such as cracks, potholes, etc.) and the severity (such as crack width, pothole depth, etc.), the road disease verification result is finally generated. The function of this layer is to conduct qualitative analysis on the disease, clarify the specific type and severity of the disease, and provide a scientific basis for subsequent maintenance decisions. Through this cascaded neural network architecture, the road damage verification model can gradually complete the detection and verification of road diseases from rough to fine, from positioning to characterization, significantly improving the accuracy and efficiency of disease recognition and laying a data foundation for the generation of work orders.

[0027] For the first-level coarse screening layer, the second-level precise positioning layer, and the third-level damage qualitative layer, they are all constructed using convolutional neural networks. The first-level coarse screening layer uses a one-dimensional convolutional neural network (1D-CNN), the second-level precise positioning layer uses a three-dimensional convolutional neural network (3D-CNN), and the third-level damage qualitative layer uses a two-dimensional convolutional neural network (2D-CNN). The training methods of these three networks are all in the form of forward propagation, loss calculation, backpropagation, and parameter optimization. Taking the first-level coarse screening layer as an example, sample vehicle vibration features and abnormal sample vehicle vibration features are extracted from the sample library, and these sample features are divided into a training set and a validation set. Subsequently, a one-dimensional convolutional neural network is used to construct the structure of the first-level coarse screening layer, including an input layer, a one-dimensional convolutional layer, a pooling layer, a fully connected layer, and an output layer, etc. Then, the weights of the one-dimensional convolutional layer, the pooling layer, the fully connected layer, and the output layer are initialized with random numbers to ensure that the model has a certain degree of randomness in the initial stage of training. After that, the training set is input into the initialized first-level coarse screening layer for forward propagation. The data passes through the input layer, the one-dimensional convolutional layer, the pooling layer, the fully connected layer, and the output layer in sequence, is transmitted layer by layer and the output result is calculated to generate abnormal vibration features. Then, the cross-entropy loss function is used to calculate the loss value between the prediction result and the abnormal sample vehicle vibration features, and the gradient of the loss with respect to the weights of each layer is calculated through backpropagation, thereby optimizing the weights of the one-dimensional convolutional layer, the pooling layer, and the fully connected layer to minimize the value of the loss function. After the training is completed, the validation set is used to test the model to evaluate its accuracy in identifying abnormal vehicle vibration features. If the accuracy meets the expected requirements, the currently trained first-level coarse screening layer is output; otherwise, hyperparameters such as the learning rate and batch size are adjusted to further optimize the model performance. After the first-level coarse screening layer is trained, after each identification of vehicle vibration features to obtain abnormal vehicle vibration features, the position information corresponding to these abnormal features is extracted from the vehicle vibration features according to the identified abnormal vehicle vibration features to form a suspected abnormal road section positioning.

[0028] According to the road disease verification result, road maintenance certification is carried out. For the roads that pass the certification, traffic flow is collected, and the maintenance priority is dynamically calculated by combining the road disease verification result and the traffic flow collection result.

[0029] In one embodiment, according to the road disease verification results, the road is first certified for repair, that is, according to the disease severity score in the road disease verification results, it is determined which roads need to be repaired. If the disease severity score of a certain road in the target roads is greater than the disease severity tolerance index, this road will be marked as to be repaired and enter the subsequent repair process. On the roads that pass the certification, the real-time traffic flow will be further collected to obtain the traffic volume of the road within the preset time window closest to the current moment. Through this traffic volume data, the current usage situation of the road can be understood, and the urgency of repairing the road can be judged. Subsequently, combining the road disease verification results and the traffic flow collection results, the repair priority is dynamically calculated. For example, if a certain section of the road is severely damaged and at the same time has a large traffic volume, the repair priority of this section of the road will be relatively high and it will be repaired first. If the road damage is minor and the traffic volume is low, the repair priority may be relatively low and may need to be adjusted according to the situation of other roads. By dynamically calculating the repair priority, the repair resources can be scientifically and reasonably allocated, the repair efficiency can be improved, and it is ensured that the roads with high traffic volume and severe diseases are repaired in time.

[0030] Furthermore, the present application provides that the calculation of the repair priority adopts the following formula:

[0031] P = α·S + β·log (1+Q) ; where P is the repair priority coefficient, S is the disease severity score, Q is the normalized real-time traffic flow, α is the first dynamic weight coefficient, and β is the second dynamic weight coefficient.

[0032] Preferably, after obtaining the road disease verification results and the traffic flow collection results, the priority of each road passing the verification is calculated using the repair priority calculation formula, and this repair priority calculation formula is specifically as follows: P = α·S + β·log (1+Q) ; where P is the repair priority coefficient, and the higher the value, the higher the repair priority; S is the disease severity score, indicating the degree of road damage, and the higher the score, the more severe the road disease; Q is the normalized real-time traffic flow, that is, the ratio of the number of vehicles passing through a certain road within the preset time window to the maximum traffic volume. The larger the traffic volume, usually the more important this road is and may require more priority repair; α is the first dynamic weight coefficient, used to adjust the influence of the disease severity on the priority; β is the second dynamic weight coefficient, used to adjust the influence of the traffic flow on the priority. Through this calculation method, the repair priorities of different roads can be dynamically determined, and the repair resources can be reasonably arranged according to the damage situation and traffic flow, laying a data foundation for the generation of road work orders.

[0033] Furthermore, the present application provides the dynamic weight coefficient, including:

[0034] Match the disease severity score with the disease severity classification table to obtain the first dynamic weight coefficient. The disease severity classification table has disease severity score classification intervals and disease classification coefficients; match the real-time traffic flow with the traffic flow classification table to obtain the second dynamic weight coefficient. The traffic flow classification table has traffic flow classification intervals and traffic flow classification coefficients.

[0035] Optionally, when calculating the maintenance priority, the weight coefficient will be dynamically adjusted according to the disease severity score and the real-time traffic flow. Specifically, match the disease severity score with a predefined disease severity classification table. The disease severity classification table contains different disease severity score classification intervals (e.g., 0.2 - 0.3 is mild, 0.3 - 0.7 is moderate, 0.7 - 1.0 is severe), and each interval corresponds to a disease classification coefficient (e.g., mild corresponds to a coefficient of 0.5, moderate corresponds to 1.0, severe corresponds to 1.5). According to the interval where the disease severity score is located, the corresponding disease classification coefficient can be obtained as the first dynamic weight coefficient. Similarly, match the real-time traffic flow with a predefined traffic flow classification table. The traffic flow classification table contains different traffic flow classification intervals (e.g., 0 - 500 vehicles / hour is low traffic, 500 - 1000 vehicles / hour is medium traffic, more than 1000 vehicles / hour is high traffic), and each interval corresponds to a traffic flow classification coefficient (e.g., low traffic corresponds to a coefficient of 0.8, medium traffic corresponds to 1.2, high traffic corresponds to 1.5). According to the interval where the real-time traffic flow is located, the corresponding traffic flow classification coefficient can be obtained as the second dynamic weight coefficient. In this way, the weights of disease severity and traffic flow in the calculation of maintenance priority can be dynamically adjusted to ensure that the generation of road work orders is more scientific and reasonable.

[0036] Return the target road, the road disease verification result, and the maintenance priority to the system, and fill in the content into the work order template according to the field names to generate the first road work order, where the first road work order has a first adaptation label.

[0037] In one embodiment, first integrate the information of the roads in the target road that need to be repaired, the road disease verification result, and the maintenance priority together. These information will be filled into the corresponding positions one by one according to the field requirements of the work order template. The work order template includes the basic information of the road, disease types, damage degree, and priority, etc. After filling, the first road work order will be generated. For the convenience of subsequent processing and tracking, the first road work order will also be given a first adaptation label, which identifies the department or personnel that can undertake this repair, helping the subsequent business distribution system to identify and distribute the work order to ensure that the work order can be processed, distributed, and archived according to the correct process.

[0038] Connect to the business distribution system and perform the distribution and archiving management of the first road work order based on the business distribution system.

[0039] In one embodiment, a communication connection is established with the service distribution system, and the generated first political work order will be distributed through the service distribution system. The service distribution system is responsible for distributing the work order to relevant departments or personnel for processing according to the first adaptation label of the first political work order, ensuring that the work order can be processed in a timely and accurate manner. At the same time, during the distribution process of the work order, distribution evidence management is executed, which means that the distribution, processing, and execution status of each work order will be recorded and archived to ensure the transparency and traceability of the process. Through this evidence management, all processing progress, decisions, and changes will be recorded in detail for subsequent viewing and auditing to ensure the compliance and efficiency of the work process.

[0040] Furthermore, the present application provides for executing the distribution evidence management of the first political work order, including:

[0041] When the first political work order is generated, the basic information of the work order is recorded on the blockchain through a smart contract to generate an initial work order record block; during the processing of the first political work order, the work order status of the first political work order is evidenced through a smart contract to generate a work order execution record block; after the first political work order is completed, a work order settlement record block is generated; wherein, the initial work order record block, the work order execution record block, and the work order settlement record block are connected according to chronological information to form a full life cycle chain of the first political work order.

[0042] Preferably, throughout the entire life cycle of the first road political work order, the whole-process deposit and management of work order data are realized through smart contracts and blockchain technology. Specifically, when the first road political work order is generated, the basic information of the work order (such as target road information, road damage verification results, maintenance priority, etc.) will be recorded on the blockchain through a smart contract, generating an initial work order record block. This block serves as the starting point of the work order life cycle, containing the creation time, content summary, and relevant responsible party information of the work order, ensuring the authenticity and immutability of the data. During the work order processing, the status of the work order (such as the work order has been distributed, maintenance in progress, maintenance completed, etc.) will be updated in real time through a smart contract and these status changes will be recorded on the blockchain, generating a work order execution record block. Each execution record block contains the status update time of the work order, operation details, and operation records of the relevant responsible party, ensuring the transparency and traceability of the work order processing. When the processing of the first road political work order is completed, the settlement information of the work order (such as maintenance completion time, maintenance quality assessment, cost settlement, etc.) will be generated and recorded on the blockchain through a smart contract, generating a work order settlement record block. This block marks the end of the work order life cycle, containing the final processing result and settlement details of the work order. The initial work order record block, work order execution record block, and work order settlement record block are connected together in chronological order to form the full life cycle chain of the first road political work order. This chain completely records the whole process of the first road political work order from generation to processing and then to completion, ensuring the continuity, transparency, and auditability of the work order data. Through blockchain technology, all participating parties can view the complete historical record of the work order but cannot tamper with the data, thereby improving the trust and efficiency of road administration management. In this way, the full life cycle management of the first road political work order is realized, ensuring the authenticity, transparency, and traceability of the work order data, and providing reliable technical support for the scientific decision-making and efficient execution of road administration management.

[0043] Furthermore, this application also includes:

[0044] Carry out business tracking on the business distribution system to obtain business processing results; analyze the business processing results to obtain feedback information; optimize the road damage verification model according to the feedback information.

[0045] Optionally, by tracking and analyzing the business processing results of the business distribution system, the road damage verification model can be further optimized. Specifically, the processing status of the first road administrative work order in the business distribution system is monitored in real time, and the entire process of the work order from distribution to completion is tracked. By recording information such as the receipt time, processing progress, and repair results of the work order, the actual execution situation of the work order can be comprehensively grasped. After the work order is processed, the processing result data is extracted from the business distribution system. This data includes information such as the repair completion time, repair quality assessment, and comparison between the actual repair content and the work order description (such as the actual location, actual disease severity score), providing a basis for subsequent analysis and optimization. Subsequently, the obtained business processing results are analyzed, the work order description comparison information is extracted therefrom, and this work order description comparison information is compared with the road disease verification result to determine whether the error of the corresponding parameter is within the tolerance range. If it exceeds the tolerance range, the work order description comparison information is stored in the feedback information library as feedback information. When the iterative update time limit is reached, the feedback information stored in the feedback information library is called to iteratively optimize the road damage verification model through steps such as forward propagation, loss calculation, backward propagation, and parameter optimization, so that the model can more accurately identify and evaluate road diseases, improving the scientificity and efficiency of the generation of road administrative work orders. Through this closed-loop feedback mechanism, the performance of the road damage verification model can be continuously improved, ensuring its accuracy and reliability in actual applications, thereby enhancing the overall level of road administration management.

[0046] In summary, the embodiments of the present application at least have the following technical effects:

[0047] In the embodiments of the present application, the vehicle-road state data of the target road is jointly collected by the in-vehicle terminal and the roadside unit. The vehicle-road state data includes vehicle vibration characteristics, road surface images, and laser point cloud data; based on the vehicle-road state data, the road damage is jointly verified to generate a road disease verification result; according to the road disease verification result, road repair certification is performed, traffic flow of the certified road is collected, and the repair priority is dynamically calculated in combination with the road disease verification result and the traffic flow collection result; the target road, the road disease verification result, and the repair priority are returned to the system, and the content is filled into the work order template according to the field name to generate a first road administrative work order, where the first road administrative work order has a first adaptation label; connect to the business distribution system and perform the distribution and storage management of the first road administrative work order based on the business distribution system. These technical effects jointly solve the technical problems that the generation of traditional road administrative work orders relies on manual input and the data verification is insufficient, resulting in low work order generation efficiency and poor accuracy, and achieve the technical effects of automatically verifying road diseases by collecting vehicle-road state data through the vehicle terminal and the roadside unit, and improving the automation degree and accuracy of the generation of road administrative work orders.

[0048] Embodiment 2. Based on the same inventive concept as the method for generating a road work order for vehicle-road intelligent collaboration in the foregoing embodiment, as Figure 2 shown, this application provides a system for generating a road work order for vehicle-road intelligent collaboration, and the system includes:

[0049] A data acquisition module 11: collaboratively acquires vehicle-road state data of a target road through an in-vehicle terminal and a roadside unit, where the vehicle-road state data includes vehicle vibration characteristics, road surface images, and lidar point cloud data; a collaborative verification module 12: performs collaborative verification on road damage based on the vehicle-road state data to generate a road disease verification result; a priority calculation module 13: performs road maintenance certification according to the road disease verification result, collects traffic flow of the road passing the certification, and dynamically calculates the maintenance priority in combination with the road disease verification result and the traffic flow collection result; a work order generation module 14: returns the target road, the road disease verification result, and the maintenance priority to the system, fills the content into a work order template according to field names, and generates a first road work order, where the first road work order has a first adaptation label; a work order distribution module 15: connects to a service distribution system and performs distribution and deposit management of the first road work order based on the service distribution system.

[0050] Further, the collaborative verification module 12 is further configured to execute the following method:

[0051] Establish a connection with the in-vehicle terminal through an in-vehicle OBD interface, and obtain vibration spectrum data of the vehicle suspension system to form vehicle vibration characteristics; use a roadside camera and a roadside lidar in the roadside unit to scan and obtain road surface images and lidar point cloud data; activate a road damage verification model, receive the vehicle vibration characteristics, road surface images, and lidar point cloud data to perform morphological analysis and verification on the target road, and generate a road disease verification result.

[0052] Further, the collaborative verification module 12 is further configured to execute the following method:

[0053] The road damage verification model includes a first-level rough screening layer, a second-level precise positioning layer, and a third-level damage characterization layer; the first-level rough screening layer uses the vehicle vibration characteristics as input data for rough positioning of disease areas and outputs positioning of suspicious abnormal road sections; the second-level precise positioning layer uses the positioning of the suspicious abnormal road sections and the lidar point cloud data as input data for damage identification to generate precise damage areas; the third-level damage characterization layer performs damage degree assessment on the precise damage areas and the road surface images to generate a road disease verification result.

[0054] Further, the priority calculation module 13 is further configured to execute the following method:

[0055] The calculation of the maintenance priority uses the following formula: P = α·S + β·log (1+Q) ; where P is the maintenance priority coefficient, S is the disease severity score, Q is the normalized real-time traffic flow, α is the first dynamic weight coefficient, and β is the second dynamic weight coefficient.

[0056] Furthermore, the priority calculation module 13 is also used to execute the following method:

[0057] Match the disease severity score with the disease severity grading table to obtain the first dynamic weight coefficient. The disease severity grading table has a disease severity score grading interval and a disease grading coefficient; match the real-time traffic flow with the traffic flow grading table to obtain the second dynamic weight coefficient. The traffic flow grading table has a traffic flow grading interval and a traffic flow grading coefficient.

[0058] Furthermore, the work order distribution module 15 is also used to execute the following method:

[0059] When the first road political work order is generated, record the basic work order information on the blockchain through a smart contract to generate an initial work order record block; during the processing of the first road political work order, use the smart contract to record the work order status of the first road political work order to generate a work order execution record block; after the first road political work order is completed, generate a work order settlement record block; among them, the initial work order record block, the work order execution record block, and the work order settlement record block are connected according to the chronological information to form the full life cycle chain of the first road political work order.

[0060] Furthermore, the work order distribution module 15 is also used to execute the following method:

[0061] Track the business of the business distribution system to obtain the business processing result; analyze the business processing result to obtain the feedback information; optimize the road damage verification model according to the feedback information.

[0062] It should be noted that the above order of the embodiments of the present application is only for description and does not represent the superiority or inferiority of the embodiments. And the above describes specific embodiments of this specification. The processes depicted in the drawings do not necessarily require the specific order and continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0063] The above are only the preferred embodiments of the present application and are not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

[0064] This specification and the drawings are merely illustrative of the present application and are considered to cover any and all modifications, variations, combinations, or equivalents within the scope of the present application. Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalent technologies, the present application is intended to include these changes and modifications therein.

Claims

1. A method for generating a road operation work order for vehicle-road intelligent collaboration, characterized in that, The method includes: Cooperatively collecting vehicle-road state data of a target road through a vehicle-mounted terminal and a roadside unit, where the vehicle-road state data includes vehicle vibration characteristics, road surface images, and lidar point cloud data; Cooperatively verifying road damage based on the vehicle-road state data to generate a road disease verification result; Conducting road maintenance certification according to the road disease verification result, collecting traffic flow of the certified road, and dynamically calculating the maintenance priority in combination with the road disease verification result and the traffic flow collection result; Returning the target road, the road disease verification result, and the maintenance priority to the system, filling the content into a work order template according to the field name to generate a first road political work order, where the first road political work order has a first adaptation label; Connecting to a service distribution system and performing distribution and deposit management of the first road political work order based on the service distribution system.

2. The method for generating a road work order for vehicle-road intelligent collaboration according to claim 1, wherein, The generating of the road disease verification result includes: Establishing a connection with the vehicle-mounted terminal through a vehicle-mounted OBD interface and obtaining vibration spectrum data of the vehicle suspension system to form vehicle vibration characteristics; Using a roadside camera and a roadside lidar in the roadside unit to scan and obtain road surface images and lidar point cloud data; Activating a road damage verification model, receiving the vehicle vibration characteristics, road surface images, and lidar point cloud data to perform morphological analysis and verification on the target road, and generating a road disease verification result.

3. The method for generating a road operation work order for vehicle-road intelligent collaboration according to claim 2, characterized in that The road damage verification model adopts a cascaded neural network architecture, including: The road damage verification model includes a first-level coarse screening layer, a second-level precise positioning layer, and a third-level damage qualification layer; The first-level coarse screening layer uses the vehicle vibration characteristics as input data to perform rough positioning of the disease area and outputs the positioning of the suspicious abnormal section; The second-level precise positioning layer uses the positioning of the suspicious abnormal section and the lidar point cloud data as input data to perform damage identification and generate an accurate damage area; The third-level damage qualification layer uses the accurate damage area and the road surface image to evaluate the damage degree and generate a road disease verification result.

4. The method for generating a road work order for vehicle-road intelligent collaboration according to claim 1, wherein The calculation of the maintenance priority adopts the following formula: P = α·S + β·log (1+Q) ; where P is the maintenance priority coefficient, S is the disease severity score, Q is the normalized real-time traffic flow, α is the first dynamic weight coefficient, and β is the second dynamic weight coefficient.

5. The method for generating a road work order for vehicle-road intelligent collaboration according to claim 4, characterized in that, Obtaining the first dynamic weight coefficient and the second dynamic weight coefficient includes: Matching the disease severity score with a disease severity grading table to obtain the first dynamic weight coefficient, where the disease severity grading table has a disease severity score grading interval and a disease grading coefficient; Matching the real-time traffic flow with a traffic flow grading table to obtain the second dynamic weight coefficient, where the traffic flow grading table has a traffic flow grading interval and a traffic flow grading coefficient.

6. The method for generating a road work order for vehicle-road intelligent collaboration according to claim 1, characterized in that, Performing the distribution and deposit management of the first road political work order includes: When the first road political work order is generated, recording the basic work order information to the blockchain through a smart contract to generate an initial work order record block; During the processing of the first road political work order, depositing the work order status of the first road political work order through a smart contract to generate a work order execution record block; After the first road political work order is completed, generating a work order settlement record block; Among them, the initial work order record block, the work order execution record block, and the work order settlement record block are connected according to chronological information to form the first full life cycle chain of the road work order for political work.

7. The method for generating a road work order for vehicle-road intelligent collaboration according to claim 3, wherein, It further includes: Conduct business tracking on the business distribution system to obtain business processing results; Analyze the business processing results to obtain feedback information; Optimize the road damage verification model according to the feedback information.

8. A road work order generation system for vehicle-road intelligent collaboration, characterized in that, The system is used to execute the method for generating a road work order for intelligent vehicle-road collaboration according to any one of claims 1-7, including: Data acquisition module: Collaborate with the roadside unit through the on-vehicle terminal to acquire the vehicle-road state data of the target road, and the vehicle-road state data includes vehicle vibration characteristics, road surface images, and laser point cloud data; Collaborative verification module: Collaboratively verify road damage based on the vehicle-road state data to generate a road disease verification result; Priority calculation module: Conduct road maintenance certification according to the road disease verification result, collect traffic flow for the roads passing the certification, and dynamically calculate the maintenance priority by combining the road disease verification result and the traffic flow collection result; Work order generation module: Return the target road, the road disease verification result, and the maintenance priority to the system, fill in the content into the work order template according to the field names, and generate the first road work order for political work, where the first road work order for political work has a first adaptation label; Work order distribution module: Connect to the business distribution system and execute the distribution and deposit management of the first road work order for political work based on the business distribution system.

Images